|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5_small_scotus |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# t5_small_scotus |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6132 |
|
- Accuracy: 0.515 |
|
- F1 Macro: 0.2879 |
|
- F1 Micro: 0.515 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0005 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 32 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.1902 | 0.32 | 50 | 2.1838 | 0.1686 | 0.0415 | 0.1686 | |
|
| 1.7893 | 0.64 | 100 | 1.8675 | 0.4436 | 0.1774 | 0.4436 | |
|
| 1.7871 | 0.96 | 150 | 1.7416 | 0.4529 | 0.2043 | 0.4529 | |
|
| 1.5347 | 1.27 | 200 | 1.6757 | 0.485 | 0.2349 | 0.485 | |
|
| 1.4821 | 1.59 | 250 | 1.6626 | 0.5079 | 0.2606 | 0.5079 | |
|
| 1.3521 | 1.91 | 300 | 1.6865 | 0.5064 | 0.2680 | 0.5064 | |
|
| 1.3616 | 2.23 | 350 | 1.6214 | 0.5093 | 0.2931 | 0.5093 | |
|
| 1.2932 | 2.55 | 400 | 1.6142 | 0.5171 | 0.2861 | 0.5171 | |
|
| 1.3028 | 2.87 | 450 | 1.6132 | 0.515 | 0.2879 | 0.515 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|